Parallel Flexible Skyline Service Discovery for QoS Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing Skyline service discovery methods face high calculation complexity and low accuracy in service selection due to serial processing and inability to handle QoS constraints, service dependency, and conflict constraints, leading to excessive or insufficient deletion of quality services.
Innovation Solution
A QoS-aware parallel flexible Skyline service discovery method that employs tournament selection, block dominance algorithms, and a flexible Skyline service correction algorithm to filter and trim candidate services across multiple parallel nodes, reducing complexity and improving accuracy by adapting to various constraints.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If serial Skyline service discovery methods are used to filter services based on QoS attributes, then service selection accuracy is maintained, but calculation complexity becomes very high due to pairwise comparisons of all services
Solution Approach 1:
The patent divides the service discovery process into multiple parallel nodes that independently process subsets of services. Each node performs local Skyline filtering on its assigned service subset, reducing the pairwise comparison complexity from O(n²) in serial processing to approximately O((n/k)²) where k is the number of parallel nodes, while maintaining overall accuracy through subsequent aggregation and correction steps.
Solution Approach 2:
The patent performs preliminary filtering of services based on hard QoS constraints before executing the Skyline algorithm. Services that do not meet minimum QoS thresholds are eliminated in advance, reducing the input size for the Skyline computation and thereby decreasing calculation complexity while preserving accuracy for services that do meet the constraints.
2Productivity
If hard Skyline services are output without considering QoS constraints and service dependencies, then calculation efficiency is improved, but service selection accuracy decreases due to excessive or insufficient deletion of quality services
Solution Approach 1:
The patent implements a feedback mechanism where the initial Skyline service set is corrected by evaluating QoS constraints, service dependencies, and conflict constraints. The correction algorithm uses information about constraint violations to adjust the service set, adding back services that were incorrectly eliminated and removing services that should not have been included, thereby improving accuracy while maintaining the efficiency gains from parallel processing.
Solution Approach 2:
The patent transitions from a static Skyline service set to a dynamic correction process that adapts to specific QoS constraints and service dependencies. The flexible Skyline service correction algorithm dynamically adjusts the service selection based on the particular constraints of each discovery task, allowing the system to maintain high calculation efficiency while achieving accurate service selection tailored to specific requirements.
3Speed
If parallel Skyline service discovery methods are used to reduce calculation complexity, then processing speed is improved, but the ability to handle QoS constraints and service dependencies is reduced
Solution Approach 1:
The patent segments the service discovery process into two distinct phases: a parallel Skyline filtering phase that achieves high processing speed, and a sequential correction phase that handles QoS constraints and service dependencies. This segmentation allows the system to exploit parallelism for the computationally intensive filtering while dedicating specific resources to constraint handling, thereby maintaining both speed and adaptability.
Solution Approach 2:
The patent introduces a flexible Skyline service correction algorithm as an intermediary between the parallel Skyline filtering process and the final service selection. This intermediary takes the efficiently computed Skyline service set and adjusts it to satisfy QoS constraints and service dependencies, acting as a bridge that preserves the speed benefits of parallel processing while ensuring constraint compliance and accurate service selection.
Data Source
AI summary
The invention relates to a quality of service (QoS)-aware parallel flexible Skyline service discovery method, including: performing, by each parallel node, a tournament selection algorithm to trim candidate services inside the parallel node; then making each parallel node perform a block dominance algorithm to filter candidate services inside the parallel node to obtain local Skyline services; collecting all local Skyline services to form a first set, and then performing filtering on the first set by using the block dominance algorithm to obtain global Skyline services; and determining whether there is a first constraint in the global Skyline services, and if yes, performing processing by using a flexible Skyline service correction algorithm to obtain a flexible Skyline service set for output, or otherwise, directly outputting the global Skyline services. The present invention reduces calculation complexity, and improves the accuracy of service selection, thereby facilitating accurate, efficient filtering to obtain quality services.